# Does Oxylabs have an MCP server?

**Yes — Official.** Oxylabs maintains an official MCP server.

> The oxylabs/oxylabs-mcp GitHub repo was archived in September 2026, while the hosted endpoint and PyPI package are still documented.

## Facts

- Verdict: Official (Yes)
- Access: Remote server — Hosted by the vendor — no install, connect over HTTP with OAuth or a token.
- Endpoint: `https://mcp.oxylabs.io/mcp`
- Package: [`oxylabs-mcp`](https://pypi.org/project/oxylabs-mcp/) on pypi
- Repository: [oxylabs/oxylabs-mcp](https://github.com/oxylabs/oxylabs-mcp) — ★ 106, last push 2026-09-07, MIT, archived
- Maintainer: Oxylabs.io
- Language: Python
- Category: [Search & Data Extraction](https://mcpyet.com/category/search-data-extraction/)
- Verified against vendor docs: 2026-09-29
- GitHub data refreshed: 2026-09-29 (re-checked every 6 hours)

## What it does

> Official Oxylabs MCP integration
> — how [oxylabs/oxylabs-mcp](https://github.com/oxylabs/oxylabs-mcp) describes itself

Project site: <https://oxylabs.io>

## The receipts

- **Vendor-hosted (remote):** `https://mcp.oxylabs.io/mcp` — a remote server run by Oxylabs itself, nothing to install. Documented at <https://developers.oxylabs.io/products/web-scraper-api/solutions-for-ai-workflows/model-context-protocol-mcp>.
- **Official package:** [`oxylabs-mcp`](https://pypi.org/project/oxylabs-mcp/) on pypi. The package page carries the exact launch arguments and required credentials.
- **Official repository:** [oxylabs/oxylabs-mcp](https://github.com/oxylabs/oxylabs-mcp) — ★ 106, pushed 2026-09-07, MIT (active), **archived**

## How to connect it

Hosted by the vendor — no install, connect over HTTP with OAuth or a token.

### Claude Code

```sh
claude mcp add --transport http oxylabs https://mcp.oxylabs.io/mcp
```

Add `--scope user` to make it available in every project.

### Claude Desktop

1. Open **Settings → Connectors**
2. Click **Add custom connector**
3. Paste `https://mcp.oxylabs.io/mcp`
4. Finish the sign-in prompt, then enable it in the chat's tools menu

### Cursor

Add to `.cursor/mcp.json` in your project, or `~/.cursor/mcp.json` for every project:

```json
{
  "mcpServers": {
    "oxylabs": {
      "url": "https://mcp.oxylabs.io/mcp"
    }
  }
}
```

### VS Code

Add to `.vscode/mcp.json`, then pick the server from Copilot's agent-mode tools menu:

```json
{
  "servers": {
    "oxylabs": {
      "type": "http",
      "url": "https://mcp.oxylabs.io/mcp"
    }
  }
}
```

### ChatGPT

1. Enable **Developer mode** under Settings → Apps & Connectors → Advanced
2. Choose **Create** and paste `https://mcp.oxylabs.io/mcp`
3. Complete sign-in, then enable the connector in a new chat

## How we know

Published to the MCP Registry under Oxylabs' verified namespace io.oxylabs and documented on developers.oxylabs.io (hosted endpoint mcp.oxylabs.io/mcp or uvx oxylabs-mcp); the hosted endpoint answers MCP initialize with 200.

- GitHub data refreshed 2026-09-29, then every 6 hours.
- Vendor docs verified on 2026-09-29.
- Corrections: hello@mcpyet.com.

## Also in Search & Data Extraction

- [Perplexity](https://mcpyet.com/mcp/perplexity.md) — Official (Yes)
- [Tavily](https://mcpyet.com/mcp/tavily.md) — Official (Yes)
- [Exa](https://mcpyet.com/mcp/exa.md) — Official (Yes)
- [Bright Data](https://mcpyet.com/mcp/bright-data.md) — Official (Yes)
- [Brave Search](https://mcpyet.com/mcp/brave-search.md) — Official (Yes)
- [SearXNG](https://mcpyet.com/mcp/searxng.md) — Community only (Sort of)

---

Source: https://mcpyet.com/mcp/oxylabs/ — data refreshed 2026-09-29